README.md

metadata

license: apache-2.0
model-index:
  - name: KoSoLAR-10.7B-v0.2_1.3_dedup_p
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: AI2 Reasoning Challenge (25-Shot)
          type: ai2_arc
          config: ARC-Challenge
          split: test
          args:
            num_few_shot: 25
        metrics:
          - type: acc_norm
            value: 63.05
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: HellaSwag (10-Shot)
          type: hellaswag
          split: validation
          args:
            num_few_shot: 10
        metrics:
          - type: acc_norm
            value: 83.63
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU (5-Shot)
          type: cais/mmlu
          config: all
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 64.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: TruthfulQA (0-shot)
          type: truthful_qa
          config: multiple_choice
          split: validation
          args:
            num_few_shot: 0
        metrics:
          - type: mc2
            value: 52.69
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: Winogrande (5-shot)
          type: winogrande
          config: winogrande_xl
          split: validation
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 80.51
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GSM8k (5-shot)
          type: gsm8k
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 48.07
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup_p
          name: Open LLM Leaderboard

Model

base_model : yanolja/KoSOLAR-10.7B-v0.2

Dataset

• 공개 데이터 수집
• Deduplicating Training Data Makes Language Models Better 알고리즘 활용

Code

from transformers import AutoModelForCausalLM, AutoTokenizer
import torch

model_name = "jingyeom/KoSoLAR-10.7B-v0.2_1.3_dedup"
model = AutoModelForCausalLM.from_pretrained(
        model_name,
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

Benchmark

Ko-LLM-Leaderboard

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	65.43
AI2 Reasoning Challenge (25-Shot)	63.05
HellaSwag (10-Shot)	83.63
MMLU (5-Shot)	64.61
TruthfulQA (0-shot)	52.69
Winogrande (5-shot)	80.51
GSM8k (5-shot)	48.07